And without any additional sensors.

This is a control theory problem: creating an observer, a model of the state of an unmeasurable quantity that you want to control, from limited data indirectly related to what you want, and using that to make control outputs, in a stable manner.

Once you reach the limits of friction, and then some external factor surprises you (such as a little bump in the pavement which briefly lightens your car, resulting in newly greatly reduced friction), what will the great technology do to compensate? I can tell you - for a brief period, its compensation will have minimal benefit. But meanwhile, your momentum will happily carry you on in the direction you were traveling when you hit that bump.

"Real time" in a mechanical system is pretty generous compared to electrical systems. Changes are in the timescale of 1 to 100 hz compared to the kHz (or even MHz) switching speeds of many electrical systems. Once you switch away from the large rotating mass of an engine (+ drivetrain), you get pretty much instantaneous torque response on an electric motor for free.

I'd say it's more interesting that they were able to figure out the delta between driver intent and physical response without adding any sensors. Having that much flexibility in the firmware of multiple control units (probably collaborating between several vendors) was likely a more complex challenge.

This is a basic property of any 3-phase AC VFD motor, it's hard to see what's special here compared to a traditional electric drivetrain.

Like ABS?